What question did this study set out to answer?

The study aims to enhance wheat yield predictions using UAV-RGB and multispectral satellite data through a stacked machine learning framework.

Stacked Ensemble Machine Learning for Phenological Wheat Yield Prediction from UAV-RGB and multispectral Satellite Data

View Full Paper

Ask AI

Bookmark

The study aims to enhance wheat yield predictions using UAV-RGB and multispectral satellite data through a stacked machine learning framework.
Conducted six UAV flights over a 25-acre site following the wheat growth calendar.
Computed the Visible Atmospheric Resistance Vegetation Index (VARI) from UAV images.
Calculated five vegetation indices from Sentinel-2 multispectral data.
Implemented three stacked machine learning frameworks for yield predictions across different growth stages.
Used model evaluation metrics such as R² and RMSE to assess prediction accuracy.
Achieved R² = 0.83 and RMSE = 1.78 at the maturity stage using the GBR meta-learner.
The ensemble of four models showed strong performance: R² = 0.79 and RMSE = 2.02 at the reproductive stage.
Identified key contributors to yield predictions as MSAVI, VARI, and NDRE using SHAP explainer.
Demonstrated that reproductive and maturity stages were optimal for yield modeling.

No takes yet. Share an insight, caveat, or question.

This analysis demonstrates wheat yield prediction in agricultural settings, integrating UAV and satellite data to enhance accuracy.

Arshad et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark